multilingual-dictionary-mcp
多语言词典 MCP
一个用于多语言词典查询及词汇关系的 MCP 服务器——包括同义词、反义词、上位词、下位词、部分词、翻译、词源、定义、押韵等——通过整合三个免费公共 API,覆盖所有语言:
ConceptNet — 多语言语义网络(80 多种语言,词汇关系:同义词、反义词、IsA、PartOf、RelatedTo、DerivedFrom 等)
Wiktionary — 4000 多种语言的定义、词源和发音
Datamuse — 仅限英语的实用工具(押韵、同音词、“意思相近”、拼写模式、上下文触发词)
无需 API 密钥。无需捆绑数据。只需将其插入 Claude(或任何 MCP 客户端),即可查询任何语言的词汇。
安装
通过 npm
npm install -g multilingual-dictionary-mcp通过 GitHub Packages
npm install -g @eyalm321/multilingual-dictionary-mcp --registry=https://npm.pkg.github.comClaude Desktop / Claude Code 配置
{
"mcpServers": {
"multilingual-dictionary": {
"command": "npx",
"args": ["-y", "multilingual-dictionary-mcp"]
}
}
}Related MCP server: word-orb
工具
多语言词汇关系 (ConceptNet)
所有这些工具都接受 word(单词)、ISO 639-1 language(语言)代码(默认为 en)以及 limit(限制)。适用于英语、西班牙语、法语、德语、意大利语、俄语、希伯来语、阿拉伯语、拉丁语、中文、日语等 70 多种语言。
工具 | 描述 |
| 意思相近的词 |
| 反义词 |
| 松散关联的词(RelatedTo 边) |
| 更广泛/父级概念(狗 → 哺乳动物) |
| 更具体/子级概念(狗 → 贵宾犬) |
| 部分/组件(汽车 → 车轮) |
| 包含此项的整体(车轮 → 汽车) |
| 词源词根 |
| 跨语言的同源词和共享词根 |
| 典型用途(刀 → 切割) |
| 典型动作(狗 → 吠叫) |
| 典型位置(书 → 图书馆) |
| 跨语言同义词 — 翻译单词 |
| 一次调用获取单词的所有关系 |
定义与词源 (Wiktionary)
工具 | 描述 |
| 按语言分组的定义(通过 en.wiktionary 支持 4000 多种语言) |
| 来自任何 Wiktionary 版本的简短纯文本摘要 |
| 词源部分,纯文本 |
| 发音部分(通常为 IPA) |
| 在 Wiktionary 版本中搜索匹配页面 |
| 来自任何 Wiktionary 版本的随机单词 |
英语专用工具 (Datamuse)
工具 | 描述 |
| 完全或近乎押韵的词 |
| 同音词 / 听起来相似的词 |
| 基于机器学习的“意思大致相同” — 比同义词范围更广 |
| 使用 |
| 自动补全 |
| 统计学上关联的词(牛 → 牛奶、农场) |
| 通常跟在后面的词(喝 → 咖啡) |
| 通常出现在前面的词(观众 → 俘虏) |
缓存管理
工具 | 描述 |
| 检查内存中响应缓存的命中/未命中/大小情况 |
| 通过清除缓存强制进行新的上游查询 |
缓存
每次成功的上游响应都会在服务器进程的生命周期内缓存在内存中,并以完整的请求 URL 作为键。同一会话内的后续相同调用将立即返回,而无需再次访问 ConceptNet/Wiktionary/Datamuse。
默认 TTL:24 小时
默认最大条目数:5000(LRU 淘汰机制)
dictionary_random禁用缓存(因为它本应是随机的)无磁盘持久化 — 缓存会在每次服务器启动时重建
通过环境变量进行调整:
MDM_DISABLE_CACHE=true # turn caching off
MDM_CACHE_TTL_MS=3600000 # 1 hour TTL
MDM_CACHE_MAX_ENTRIES=10000 # bigger cache示例
> What are the synonyms of "feliz" in Spanish?
[uses dictionary_synonyms with language: "es"]
> Translate "happiness" into Hebrew
[uses dictionary_translate with language: "en", targetLanguage: "he"]
> What's the etymology of the word "serendipity"?
[uses dictionary_etymology]
> Find me words that rhyme with "orange"
[uses dictionary_rhymes]
> What are the parts of a bicycle?
[uses dictionary_meronyms with word: "bicycle"]开发
npm install
npm run build # TypeScript compile
npm test # vitest run
npm run test:watch # vitest watch
npm run dev # ts-node entry point项目布局
src/
├── index.ts # MCP server entry
├── client.ts # HTTP wrappers for ConceptNet / Wiktionary / Datamuse
├── tools/
│ ├── relations.ts # ConceptNet-backed multilingual relation tools
│ ├── definitions.ts # Wiktionary-backed definition/etymology tools
│ └── english.ts # Datamuse-backed English utilities
└── __tests__/ # vitest specsCI / 发布
CI 在每次推送到
main分支以及提交 PR 时运行,基于 Node 20 和 22。发布 在发布 GitHub Release 时运行 — 执行测试、构建,然后发布到 npm(作为
multilingual-dictionary-mcp)和 GitHub Packages(作为@eyalm321/multilingual-dictionary-mcp)。
发布步骤:
在
package.json中增加version并提交。打标签并推送(例如
git tag v0.1.1 && git push --tags)。创建指向该标签的 GitHub Release — 发布工作流将处理其余事项。
发布工作流需要两个仓库密钥:NPM_TOKEN(npm 自动化令牌)和 GITHUB_TOKEN(由 GitHub Actions 自动提供)。
许可证
MIT © Eyalm321
Available Tools
28 toolsdictionary_all_relationsC
All edges (every relation type) for a word in one call from offline ConceptNet.
Inputs: word (required), limit, language.
dictionary_antonymsB
Get antonyms (opposites) for a word in any language using offline ConceptNet.
Inputs: word (required), limit, language.
dictionary_at_locationB
Typical locations (AtLocation) via offline ConceptNet. E.g. book -> library.
Inputs: word (required), limit, language.
dictionary_capable_ofB
Typical actions (CapableOf) via offline ConceptNet. E.g. dog -> bark.
Inputs: word (required), limit, language.
dictionary_derived_fromC
Derivation relations via offline ConceptNet DerivedFrom.
Inputs: word (required), limit, language.
dictionary_etymologyA
Return etymology text for a word from the offline Wiktextract corpus.
Inputs: word (required), language.
dictionary_holonymsB
Holonyms (wholes that contain this word) via offline ConceptNet reverse PartOf.
Inputs: word (required), limit, language.
dictionary_hypernymsA
Hypernyms (broader concepts) via offline ConceptNet IsA. E.g. dog -> mammal.
Inputs: word (required), limit, language.
dictionary_hyponymsB
Hyponyms (narrower concepts) via offline ConceptNet IsA. E.g. dog -> poodle.
Inputs: word (required), limit, language.
dictionary_installA
Manually kick off (or re-trigger) the offline data download. Returns immediately while the install runs in the background. Idempotent — calling repeatedly while a download is in progress is a no-op. Use dictionary_status to track progress.
Inputs: no named parameters.
dictionary_lookupA
Look up definitions for a word from the offline Wiktextract corpus (4,755 languages, 10.5M entries). Returns part-of-speech, definitions per sense, IPA, etymology, and translations grouped by language.
Inputs: word (required), limit, language.
dictionary_means_likeA
Find words/phrases meaning approximately the same as the input via offline Numberbatch embedding cosine. Multilingual — works in any of the 78 languages Numberbatch covers.
Inputs: query (required), limit, language.
dictionary_meronymsC
Meronyms (parts/components) via offline ConceptNet PartOf. E.g. car -> wheel.
Inputs: word (required), limit, language.
dictionary_pronunciationB
Return IPA pronunciation(s) for a word from the offline Wiktextract corpus.
Inputs: word (required), language.
dictionary_randomA
Return a random word entry from the offline Wiktextract corpus, optionally filtered to a language.
Inputs: language.
dictionary_rhymesA
Find words that rhyme with the input word. English only — backed by the offline CMU Pronouncing Dictionary.
Inputs: word (required), limit, perfect.
dictionary_searchA
Prefix-search the offline Wiktextract corpus for words matching a query. Useful when you don't know the exact spelling.
Inputs: query (required), limit, language.
dictionary_semantic_neighborsA
Embedding-based nearest neighbors via Numberbatch. Returns words from the same OR a different language, sorted by cosine similarity. Multilingual (78 languages).
Inputs: word (required), limit, language, targetLanguage.
dictionary_sounds_likeB
Find English words that sound similar to the input (homophones / soundalikes) via offline CMU dict.
Inputs: word (required), limit.
dictionary_spelled_likeA
Find English words matching a spelling pattern via offline CMU dict. '?' = any single letter, '*' = any zero+ letters. Useful for crosswords.
Inputs: pattern (required), limit.
dictionary_statusA
Get the current state of the offline data installation. Always available — even before the bundle has finished downloading. Returns: state (pending/downloading/ready/failed), per-artifact progress, total bytes downloaded, data directory, CDN URL, manifest version, and any error.
Inputs: no named parameters.
dictionary_suggestA
Get autocomplete suggestions for a partial English word via offline CMU dict (shortest matches first).
Inputs: prefix (required), limit.
dictionary_summaryA
Get a brief plain-text summary of a word's senses from the offline Wiktextract data. Concatenates the first definition of each sense.
Inputs: word (required), language.
dictionary_synonymsA
Get synonyms for a word in any language using the offline ConceptNet 5.7 SQLite (24M edges, 80+ languages).
Inputs: word (required), limit, language.
dictionary_translateC
Translate a word to another language via offline ConceptNet's cross-lingual Synonym links. Returns the same concept expressed in different languages.
Inputs: word (required), limit, language, targetLanguage.
dictionary_used_forB
Typical uses (UsedFor) via offline ConceptNet. E.g. knife -> cutting.
Inputs: word (required), limit, language.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 28 tools
Each tool targets a specific linguistic relation or operation with clear, distinct descriptions. Even potentially overlapping tools like synonyms, means_like, and related are differentiated by their underlying data sources (ConceptNet vs Numberbatch embeddings).
All tools follow a consistent 'dictionary_' prefix followed by a descriptive snake_case name. The pattern is uniform with no mixing of conventions or styles.
28 tools is on the higher end but justified by the comprehensive coverage of dictionary features (definitions, etymology, pronunciation, semantic relations, search, data management). It remains manageable and focused.
The tool surface covers a wide range of dictionary and lexical relations: definitions, pronunciations, etymology, synonyms, antonyms, hypernyms, hyponyms, meronyms, holonyms, translations, rhymes, spelling, autocomplete, random access, and data installation status. No obvious gaps for the stated purpose.
Maintenance
Related MCP Connectors
MCP server for Chinese dictionary lookup: character definitions, pinyin, stroke order and word
Wiktionary MCP — multilingual dictionary via Wikimedia REST + MediaWiki Action API
Unofficial Dictionary MCP — wraps Free Dictionary API (free, no auth)
MCP server for Chinese idioms (chengyu): lookup by word, pinyin or meaning with explanation and
Related MCP Servers
- AlicenseCqualityDmaintenanceAn MCP server that provides access to the Similar Words API, allowing users to search for and retrieve semantically related words. It enables language-based applications to query word similarities and relationships through a standardized interface.1MIT
- AlicenseNot gradedqualityCmaintenanceVocabulary intelligence MCP server — 162K words, 47 languages, definitions, IPA pronunciation, etymology, translations, and daily lessons. 19 tools for AI agents.1MIT
- AlicenseAqualityDmaintenanceMCP server for the Datamuse API that enables word finding like synonyms, rhymes, autocomplete, and more.1049 npm3MIT
- FlicenseNot gradedqualityDmaintenanceRemote MCP server for word definitions and random word retrieval via Oxford Dictionaries API, deployable on Vercel with bearer token authentication.-